Knowledge catalogue
'Claude Code isn't magic. The harness layer is just software, and software is something any dev can shape to fit how they want to work.' Check out @Hacubu’s practical guide to building a custom agent
Highlights: 👉 28% coding improvement over GLM-5 with refined RL post-training 👉 Better long-horizon execution across hundreds of rounds and thousands of tool calls 👉 Thinking mode, tool calling, and s
The specific post at status ID `2041927488918413589` could not be retrieved directly, as it did not appear in search results. However, based on the surrounding context from the same account (@Vtriv...
If you're an AI/agent builder, it's so important that you don't overbuild and overcommit on a specific toolset and infrastructure. Frontier labs are shipping not just the models, but the harnesses and
Proud to power @NousResearch's Hermes Agent with MiniMax M2.7, and excited for what we're building together. Try MiniMax M2.7 in Hermes Agent today → https://portal.nousresearch.com #MiniMax #NousRese
> which is exactly why we believe memory should live outside of model providers open harness = open memory which everyone should want! The new Anthropic managed agents API is basically the Letta API t
Atlassian reports 30.8% lower median PR cycle time in an internal evaluation of Claude-backed Rovo Dev Code Reviewer.
Mem0 documents a self-hosted agent-memory REST API with a pgvector vector store and Neo4j knowledge graph; local models are optional.
Anthropic reports Zapier uses Claude in marketing, engineering, research and design; its AI-wide adoption figures are not Claude-only.
AI research and deployment company behind ChatGPT, the GPT model family, Codex, and the OpenAI API — heavily represented in this wiki’s model-releases and safety corpus.
arXiv:2606.17090v2 Announce Type: replace-cross Abstract: ANEForge is a Python package that programs the Apple Neural Engine (ANE), the fixed-function neural accelerator on every recent Apple device,
arXiv:2610.22230v1 Announce Type: cross Abstract: Meta deploys a heterogeneous fleet comprising NVIDIA GPUs, AMD GPUs, and proprietary MTIA accelerators to reduce costs and mitigate vendor lock-in. Ho
arXiv:2610.21325v1 Announce Type: new Abstract: Exact k-nearest-neighbor (kNN) search over image descriptors and embeddings underlies visual retrieval, near-duplicate detection, the evaluation of lear
arXiv:2610.22160v1 Announce Type: cross Abstract: Test-time context optimization adapts frozen language models through textual feedback, but ordinary conditional generation provides no separate contro
// FDE-Gym: Agents as Forward-Deployed Engineers // They found that the best agent configuration fully resolved 14 of 95 real customer-delivery tasks. FDE-Gym tests agents as forward-deployed engineer
arXiv:2610.22350v1 Announce Type: new Abstract: Existing agent benchmarks typically evaluate agents on well-specified tasks defined by issue reports, specifications, or task tickets. Real-world custom
arXiv:2610.21351v1 Announce Type: new Abstract: To enable well-informed customer choices and redistribute demand across service options, providers can display probabilities regarding predicted service
arXiv:2610.21503v1 Announce Type: new Abstract: Reliable worker localization is essential for real-time industrial safety management, but seamless outdoor-indoor positioning remains challenging. GNSS
arXiv:2610.21394v1 Announce Type: cross Abstract: Matoi separates reusable consequence evidence from current execution authority and durable occurrence history. Its finite query-aware contract covers
arXiv:2610.21314v1 Announce Type: new Abstract: Money-mule networks move criminal funds through many small transfers, each of which looks ordinary on its own. What marks an account as a mule lies outs
arXiv:2610.20993v1 Announce Type: new Abstract: Reordering multiple-choice options can change a model's answer, an effect studied as selection bias (a preference for certain option letters) and as ord
arXiv:2610.20873v1 Announce Type: new Abstract: Vehicles that lose control at the handling limit through icing, hydroplaning, or an abrupt evasive maneuver fall outside the operating envelope of produ
Title: I'm building a small local AI server to validate a project I've developed. The application currently runs Qwen 9B and the server will only be used for an initial pilot with a few users. I have
arXiv:2610.21049v1 Announce Type: new Abstract: Learned dynamical models can accurately predict trajectories while producing unreliable sensitivities when differentiated or transposed, limiting their
arXiv:2610.20941v1 Announce Type: cross Abstract: We present Screwtape, a pipeline that converts real agent transcripts into attacks that evade action-only monitors. An LLM attacker edits a transcript
arXiv:2507.03411v2 Announce Type: replace Abstract: In the era of Industry 5.0, data-driven decision-making has become indispensable for planning in service systems such as tourism. This paper propose
arXiv:2610.21999v1 Announce Type: new Abstract: Embodied Visual Tracking (EVT) is an essential capability for intelligent robots in human-robot collaboration, requiring an agent to follow a designated
We've released the weights for Beam!! 🤗 https://huggingface.co/reflection 📄 Model card: https://reflection.ai/beam-model-card 🧪 Try Beam in our playground & get an API key: https://platform.reflection
arXiv:2610.21553v1 Announce Type: new Abstract: Addressed conditional memory provides a local surface for post-hoc knowledge injection, but a successful write need not transfer to a new question or pr
arXiv:2610.21320v1 Announce Type: cross Abstract: Detailed captions transfer visual information into vision-language model supervision, but quality is easily conflated with length: long single-pass ou
A big Google strength in AI has always been finding interesting uses for the models they have. They pioneered deep research, podcasting-from-information and all of NotebookLM etc. With Gemini 4, haven
arXiv:2610.19607v1 Announce Type: cross Abstract: Rising privacy concerns around large language models have accelerated research in private Transformer inference (PTI). Synthesizing the empirical clai
arXiv:2610.19999v1 Announce Type: new Abstract: Legal-content reproduction requires matching the source exactly in section hierarchy, verbatim text, citations, and amendment spans; a dropped citation
arXiv:2610.19404v1 Announce Type: cross Abstract: Reticular chemistry allows metal-organic frameworks (MOFs) to be designed from their building units, yet their synthesis remains constrained by sparse
arXiv:2610.19154v1 Announce Type: new Abstract: Field pea has gained interest in the Midwest U.S. and has the potential to benefit Iowa cropping systems. This study evaluated 17 accessions and 7 Canad
Scott Alexander / Astral Codex Ten: AI industry extinction warnings are genuine rather than corporate plots for regulatory capture or hype, and they go as far back as the mid-2000s and the 2010s — AI
Bloomberg: Amazon launches two AI wearables, the 75 Bee Frontier wristband and 100 Bee Eclipse magnetic phone-attachment recorder, with a $12/month Bee Pro subscription — Amazon.com Inc. launched two
ggml-cpu : keep the FP16->FP32 lookup table on x86 with F16C (#30342) (#30343) ggml-cpu : keep the FP16->FP32 lookup table on x86 with F16C (#30342) #30270 routed both scalar conversions through F16C.
sycl: IQ3 code reorder (#29107) sycl: persistent IQ3_S/IQ3_XXS weight reorder for SYCL decode and prefill Add persistent reordered weight layouts for IQ3_S and IQ3_XXS. Weights are reordered once at l
arXiv:2610.19603v1 Announce Type: new Abstract: Transformers have demonstrated strong performance in long-term time series forecasting (LTSF), yet modeling non-stationary temporal dependencies remains
arXiv:2602.08519v2 Announce Type: replace Abstract: Attributed Graph Clustering (AGC) is a fundamental unsupervised task that integrates structural topology and node attributes to uncover latent patte
arXiv:2610.16415v1 Announce Type: new Abstract: Industrial recommendation rankers keep scaling in width and depth to billions of parameters, but this increasingly incurs costs in parameter growth, dis
arXiv:2610.15239v1 Announce Type: new Abstract: Most benchmarks for large language models in medicine are built from licensing examinations and theoretical questions. The few that draw on real clinica
arXiv:2610.19540v1 Announce Type: new Abstract: Automated defect detection of industrial boards must remain highly reliable under cross-scenario variations in lighting, surface contaminants, and produ
arXiv:2610.17831v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) are appealing for code generation because they can update many tokens in parallel, yet many are optimized for
arXiv:2610.16402v1 Announce Type: new Abstract: Web application development often proceeds through successive requests that extend an existing implementation. Yet web-generation benchmarks primarily e
arXiv:2610.19893v1 Announce Type: cross Abstract: Reliable fault detection is crucial for industrial machinery in large-scale facilities, where unexpected failures can cause costly downtime and produc
arXiv:2604.06138v2 Announce Type: replace-cross Abstract: Long-context audio reasoning is underserved in both training data and evaluation. Existing benchmarks target short-context tasks, and the open
arXiv:2610.16998v1 Announce Type: new Abstract: Deep search enables language agents to solve complex information-seeking tasks through iterative web exploration. However, developing robust open-source
arXiv:2610.16319v1 Announce Type: new Abstract: Real-world hybrid web tasks need both information gathering and page interaction, yet search-based and operation-based agents are developed and evaluate
Introducing ExtractBenchPro: the most challenging benchmark for real-world document extraction. We see a massive long tail of document complexity in terms of use cases brought on from our customers, t
arXiv:2610.19290v1 Announce Type: new Abstract: We present Kandinsky S2V 1.0, an open family of speech-to-video models for controllable audio-driven human animation, comprising Kandinsky S2V 1.0 Lite
arXiv:2610.16231v1 Announce Type: new Abstract: As large language models are increasingly adopted as multi-party communication facilitators, there is a growing demand for agents capable of balancing d
arXiv:2608.28281v2 Announce Type: replace Abstract: Loop Engineering is emerging as a practice for organizing development work around coding agents. Instead of writing each prompt by hand, practitione
arXiv:2610.16298v1 Announce Type: new Abstract: Training neural networks in reduced precision can yield significant efficiency gains, yet all existing methods that scale to standard computer vision be
Muse Spark Open is now live on Together AI. We're proud to be a Day 0 launch partner for @AIatMeta's Muse Spark Open, the most capable US open-weights model to date, built for long-running agentic cod
New work from Meta AI on agents that manage their own search. (bookmark it) A ReAct agent keeps every failed attempt in one context, making useful evidence harder to find. To improve on this, they pro
arXiv:2610.19605v1 Announce Type: cross Abstract: Long-output inference in large language models suffers from severe KV cache memory and bandwidth bottlenecks. While KV cache quantization alleviates t
arXiv:2610.14912v1 Announce Type: new Abstract: Language models are increasingly used to create synthetic survey samples, also called silicon samples. Decision models are a new class of language model
Cybersecurity company Proofpoint Inc. today unveiled new Microsoft 365 security features meant to get managed service providers and the businesses they look after ready to adopt artificial intelligenc